Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert.
Listed on
First seen 2 Oct 2026. One server, whatever directories list it: each directory listing keeps its own page and history.
1
Directories
Collected by InvokeRank
68
Tools
From an anonymous probe
-
ToolBench grade
Not graded by Arcade
4
GitHub stars
From MCP Toplist
Tools
| Tool | Description | Behaviour |
|---|---|---|
| agents_contradiction | [agents] Detect contradictions between two free-text agent outputs (natural-language claim drift). For structured key/value claims that must agree, use detect_contradiction instead. | Read-only |
| agents_intent_classify | [agents] Agent intent classification | Read-only |
| agents_plan | [agents] Autonomous agent goal planning | Read-only |
| agents_register | [agents] Register an agent | Changes data |
| agents_reputation | [agents] Agent reputation and trust score | Read-only |
| agents_semantic_diff | [agents] Semantic diff between two free-text agent outputs (meaning-level change, not text-level). Use forge_verify for build artifacts and drift_check for certified operational drift. | Read-only |
| agents_topology | [agents] Live swarm topology | Read-only |
| audit_work_claim | [Ledger product, entitlement: ledger] Recompute-audit an agent work claim: re-derive a deterministic SHA-256 digest from the claimed inputs and check it against the claimed digest. Returns GREEN (matches), RED (tampered), or UNVERIFIED (no claim supplied). Replay, not opinion. 3 free calls/day, then entitlement 'ledger'. | Changes data |
| compliance_check | [security] Delegation-depth + KL gate (GOV-100). Reads chain_depth and kl_divergence. It does NOT read your data description and does NOT evaluate GDPR/CCPA - compliant:true only means the delegation chain is shallow and KL is under epsilon. | Read-only |
| compliance_eu_ai_act | [security] EU AI Act compliance certificate | Read-only |
| compliance_explain | [security] Explainability certificate (XPL-100-ExplainBound) | Read-only |
| compliance_fairness | [security] Fairness proof (FNS-100-FairnessBound) | Read-only |
| compliance_incident | [security] Report compliance incident | Changes data |
| compliance_incidents | [security] Incident registry | Read-only |
| compliance_lineage | [security] Data lineage (LIN-100-ChainIntegrity) | Read-only |
| compliance_oversight | [security] Log oversight event | Read-only |
| compliance_oversight_history | [security] Oversight history | Read-only |
| compliance_transparency | [security] Transparency report | Read-only |
| defi_bridge_verify | [defi] Bridge Proof (BRP-100-BridgeIntegrity) | Read-only |
| defi_contract_audit | [defi] Contract Verify (CVR-100-AuditBound) | Read-only |
| defi_liquidation_check | [defi] Liquid Shield (LQS-100-LiquidationBound) | Read-only |
| defi_optimize | [defi] LP parameter optimization (DFP-100-OptimalTick) | Changes data |
| defi_oracle_verify | [defi] Oracle guard (OGD-100-ManipulationBound) | Read-only |
| defi_risk_score | [defi] DeFi risk scoring (DFI-101-RiskScoreBound) | Read-only |
| defi_yield_optimize | [defi] Yield Oracle (YLD-100-YieldConvergence) | Changes data |
| detect_contradiction | [Ledger product, entitlement: ledger] Detect contradictions across structured claims: the same key asserted with conflicting values flips RED, otherwise GREEN. Deterministic and recomputable. Use agents_contradiction instead when comparing free-text agent prose. 3 free calls/day, then entitlement 'ledger'. | Read-only |
| drift_certificate | [trust] Drift certificate | Read-only |
| drift_check | [trust] DriftGuard check (DRG-100-DriftBound) | Read-only |
| enforce_sla | [Ledger product, entitlement: ledger] Enforce an SLA/obligation by recomputation: the obligation is met only if the work verifies GREEN against its claimed digest. 3 free calls/day, then entitlement 'ledger'. | Changes data |
| escrow_create | [defi] Create agent-to-agent escrow | Changes data |
| escrow_dispute | [defi] Open escrow dispute | Destructive |
| escrow_release | [defi] Release escrowed funds | Destructive |
| forge_badge | [fuse] Model quality badge | Read-only |
| forge_delta_submit | [fuse] Submit a model delta | Changes data |
| forge_leaderboard | [fuse] Model leaderboard | Read-only |
| forge_quarantine | [fuse] Quarantined models | Destructive |
| forge_verify | [fuse] Verify a model submission | Read-only |
| identity_sybil_check | [identity] Sybil-resistance check | Read-only |
| identity_verify | [identity] Topological identity verification | Read-only |
| inference | [inference] Chat inference with hallucination guard | Read-only |
| inference_stream | [inference] Streaming inference with chain-of-thought | Read-only |
| murmuration | START HERE (free, no key). Initialize your Atomadic control surface in one call: returns a verbose, step-by-step setup (SDK install, MCP connect, your unlocked tools), a RUNNABLE polyglot demo that proves the superpowers, recon links, and a one-command bootstrap. Idempotent — re-call anytime to re-check. | Changes data |
| oracle_entropy | [trust] Entropy epoch oracle | Read-only |
| oracle_hallucination | [trust] Hallucination oracle | Read-only |
| rag_augment | [inference] Trusted RAG augmentation | Read-only |
| ratchet_advance | [identity] RatchetGate — advance session | Changes data |
| ratchet_probe | [identity] RatchetGate — health probe | Read-only |
| ratchet_register | [identity] RatchetGate — register session | Changes data |
| receipt_reputation | [Ledger product, entitlement: ledger] Compute an agent's reputation from a ledger of verifiable receipts (verified minus refuted), deterministically - not from vibes or LLM judgment. 3 free calls/day, then entitlement 'ledger'. | Changes data |
| render_polyglot_all_pure | [Fuse product · entitlement: fuse · FREE_R2_DEMO] Polyglot emit to all 7 supported targets in one call. Returns {ok, ir, results, languages}. Canonical demo examples baked to R2; novel inputs via SDK. | Read-only |
| render_polyglot_roundtrip_pure | [Fuse product · entitlement: fuse · FREE_R2_DEMO] Syntax-as-Data polyglot render head: source -> language-neutral logic IR -> source in target language. Canonical demo examples baked to R2 (4 examples × 12 languages). Live emit of novel inputs via the SDK. | Read-only |
| reputation_record | [agents] Record agent interaction | Changes data |
| rng_quantum | [inference] Quantum random number with proof | Read-only |
| rng_verify | [inference] Verify current epoch random value | Read-only |
| route_capability | [Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'. | Read-only |
| security_zero_day | [security] Zero-day threat assessment | Read-only |
| sla_register | [agents] Register an SLA | Changes data |
| sla_report | [agents] Report SLA violation | Changes data |
| swarm_inbox | [agents] Poll swarm inbox | Read-only |
| swarm_relay | [agents] Relay message through swarm | Changes data |
| text_keywords | [inference] Keyword extraction | Read-only |
| text_sentiment | [inference] Sentiment analysis | Read-only |
| text_summarize | [inference] Text summarization | Read-only |
| threat_score | [security] Multi-vector threat score | Read-only |
| trust_decay | [trust] Current trust ceiling value | Read-only |
| trust_history | [trust] Trust score history | Read-only |
| trust_score | [trust] Bounded trust score | Read-only |
| verify_settlement | [Ledger product, entitlement: ledger] Proof-gated settlement: recompute the work digest and authorize a payout only if the claimed digest verifies GREEN. No proof, no payout. 3 free calls/day, then entitlement 'ledger'. | Changes data |
| Directory | Listing | Tier | First seen |
|---|---|---|---|
| Official MCP Registry | Atomadic Forge | - | 2 Oct 2026 |